Files
actionbook__actionbook/docs/index.mdx
2026-02-13 23:41:14 +08:00

107 lines
3.4 KiB
Plaintext
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
---
title: 'Introduction'
description: 'Make agents browse 10× faster with unbreakable resilience.'
---
Actionbook gives LLMs up-to-date DOM structure and action guides. Install the CLI and start automating in minutes.
<video
controls
className="w-full aspect-video rounded-xl"
src="/actionbook-demo.mp4"
/>
_See how Actionbook enables an agent to complete an Airbnb search task 10× faster._
## Why Actionbook?
### <Icon icon="xmark" color="#ef4444" /> Without Actionbook
Building reliable browser agents is difficult and expensive:
- **Slow Execution:** Agents waste time parsing full HTML pages to find elements
- **High Token Costs:** Sending entire DOM trees to LLMs consumes massive context windows
- **Brittle Selectors:** Updates to website UIs break hardcoded selectors and agent logic immediately
- **Hallucinations:** LLMs often guess incorrect actions when faced with complex, unstructured DOMs
### <Icon icon="check" color="#22c55e" /> With Actionbook
Actionbook places up-to-date action manuals with the relevant DOM selectors directly into your LLM's context:
- **10x Faster:** Agents access pre-computed "Action manuals" to know exactly what to do without exploring
- **100x Token Savings:** Instead of whole HTML page, agents receive only related DOM elements in concise, semantic JSON definitions
- **Resilient Automation:** Action manuals are maintained and versioned. If a site changes, the manual is updated, not your agent
- **Universal Compatibility:** Works with any LLM (OpenAI, Anthropic, Gemini) and any AI operator framework
## How It Works
<Steps>
<Step title="Search for Actions" icon="magnifying-glass">
Find available actions for any website using the CLI (`actionbook search
"airbnb login"`).
</Step>
<Step title="Get Action Details" icon="book">
Retrieve the full action manual with precise selectors and step-by-step
instructions (`actionbook get "google.com:/:default"`).
</Step>
<Step title="Launch & Execute" icon="bullseye">
Open a browser session and let your agent execute actions with confidence —
no guessing, no hallucinations (`actionbook browser open
"https://www.google.com"`).
</Step>
</Steps>
## Integration Options
<Columns cols={3}>
<Card title="CLI" icon="terminal" href="/quickstart">
Default mode — launches browser automatically
</Card>
<Card title="Browser Automation" icon="window" href="/guides/browser">
Isolated or extension — two modes for AI agents
</Card>
<Card title="MCP Server" icon="server" href="/guides/mcp-server">
Integrate with Cursor, Claude Code, VS Code, etc.
</Card>
</Columns>
## Quick Start
<Columns cols={2}>
<Card title="Quickstart Guide" icon="rocket" href="/quickstart">
Get started in under 2 minutes
</Card>
<Card title="API Reference" icon="code" href="/api-reference/cli">
CLI commands and API documentation
</Card>
</Columns>
## Community
<Columns cols={3}>
<Card
title="GitHub"
icon="github"
iconType="brands"
href="https://github.com/actionbook/actionbook"
>
Star us and contribute
</Card>
<Card
title="Discord"
icon="discord"
iconType="brands"
href="https://actionbook.dev/discord"
>
Get help and share your agents
</Card>
<Card
title="X / Twitter"
icon="x-twitter"
iconType="brands"
href="https://x.com/ActionbookHQ"
>
Product updates and announcements
</Card>
</Columns>